Footwear Type Estimation Using Gait Feature Extraction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing technologies are unable to accurately estimate the type of footwear worn by a pedestrian based on gait features, as they either require sensors on the footwear or rely on floor vibration waveforms that cannot measure heel height.

Innovation Solution

An estimation device that includes a data acquisition unit to collect sensor data from footwear, extract gait feature quantities, and an estimation unit to determine the type of footwear using machine-learning models.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If sensor data is acquired from footwear to estimate footwear type, then measurement precision is improved, but device complexity increases

Engineering Contradiction:

Improvefootwear type estimation accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The sensor system originally designed for gait analysis is made multi-functional by adding footwear type estimation capability. The same acceleration sensors and processing algorithms serve both gait feature extraction and footwear classification, eliminating the need for separate dedicated sensors and reducing overall system complexity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system estimates footwear type by analyzing changes in gait parameter patterns rather than directly measuring footwear characteristics. By monitoring how gait parameters (acceleration patterns, timing, intensity) change when different footwear is worn, the system achieves accurate classification without requiring specialized sensors.

Inventive Principle:

Principle #35Parameter changes

2Loss of information

If gait feature quantity is extracted from sensor data, then information about footwear is obtained, but loss of information occurs

Engineering Contradiction:

Improvefootwear characteristic informationVSAvoidfootwear type identification accuracy

Core Design Contradiction:

Loss of informationVSMeasurement precision

Solution Approach 1:

The system extracts specific footwear-related information from comprehensive gait data by identifying and isolating characteristic patterns. Instead of attempting to preserve all raw sensor data, the system extracts key gait features (timing, acceleration patterns, temporal characteristics) that specifically indicate footwear type, discarding redundant information.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

Gait feature quantities serve as intermediary representations between raw sensor data and footwear type classification. The system transforms complex multi-dimensional sensor data into simplified gait features that retain essential footwear-related information while reducing data complexity and preventing information loss during processing.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS12551139B2Estimation device, estimation system, estimation method, and program recording medium

Publication Date: 2026.02.17 NEC CORP

AI summary

In order to estimate the type of footwear worn by a pedestrian, an estimation device and the like according to the present invention are provided with: an extraction unit which acquires sensor data from a sensor installed on the footwear, and uses the sensor data to extract a walking feature quantity characteristic of walking in footwear; and an estimation unit which estimates the type of footwear on the basis of the walking feature quantity extracted by the extraction unit.